INDEX

Explanations

references to missing persons or categories related to demographics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

meli

-0.16

ialog

-0.15

ÄĻ

-0.15

 Minor

-0.15

 Abrams

-0.14

 Nash

-0.14

ÑĮÐµ

-0.14

-u

-0.14

menin

-0.14

-0.13

POSITIVE LOGITS

.Ac

0.16

_drv

0.16

åĵ

0.15

appe

0.15

ac

0.15

åħ³

0.15

asar

0.14

çĨŁ

0.14

zb

0.14

ycop

0.14

Activations Density 0.060%

references to missing persons or categories related to demographics

No Comments

No Known Activations